Datasheet for local AI49 models98 GPUsData read 2026-09-25
No adsNo tracking
Check my GPU →

RTX 3080 10 GB for local AI

Which image and video models run on the RTX 3080 10 GB, which file to download for each, and how much VRAM they need.

NVIDIA10 GB GDDR6X · 320-bit · 760 GB/s · AmpereData 2026-09-25
VRAM10 GB
MemoryGDDR6X
Bus320-bit
Bandwidth760 GB/s
ArchitectureAmpere
Launched2020-09
Launch price$699
Runs well12 of 49

Specs: www.nvidia.com · launch: en.wikipedia.org

01What runs on it

ModelVerdictBest fileSizeNeeded
image models
FLUX.1 [dev]RunsQ4_K_S6.8 GB9.1 GB
FLUX.1 [schnell]RunsQ4_K_S6.8 GB9.1 GB
FLUX.1 Kontext [dev]RunsQ4_K_M6.9 GB9.5 GB
FLUX.1 Krea [dev]RunsQ4_K_M6.9 GB9.2 GB
FLUX.1 Fill [dev]RunsQ4_K_S6.8 GB9.4 GB
FLUX.2 [dev]Not practicalQ2_K12.9 GB16.2 GB
FLUX.2 [klein] 9BRunsQ5_K_M7.0 GB9.3 GB
FLUX.2 [klein] 4BRuns well16-bit7.8 GB9.6 GB
Krea 2 (Turbo)TightQ3_K_M6.0 GB8.6 GB
Qwen-ImageTightQ2_K7.1 GB9.9 GB
Qwen-Image-Edit (2511)Offload onlyQ2_K7.5 GB10.5 GB
Qwen-Image 2.1Runs wellQ8_07.6 GB9.9 GB
Z-Image TurboRuns wellQ8_07.2 GB9.2 GB
Z-Image (base)Runs wellQ8_07.2 GB9.2 GB
Ideogram 4Offload onlyQ4_16.2 GB14.7 GB
Boogu-Image (Turbo)Offload onlyQ5_18.6 GB11.2 GB
ERNIE-Image (Turbo)RunsQ6_K6.8 GB9.1 GB
HiDream-O1-ImageOffload onlyFP88.1 GB10.9 GB
Mage-Flow (Microsoft)Runs wellINT84.2 GB6.0 GB
Lumina Image 2.0Runs well16-bit5.2 GB7.0 GB
HiDream-I1 (Full)TightQ2_K6.6 GB9.4 GB
HiDream-I1 (Dev)TightQ2_K6.6 GB9.4 GB
Stable Diffusion 3.5 LargeRunsQ5_16.3 GB8.6 GB
Stable Diffusion 3.5 MediumRuns well16-bit5.1 GB6.9 GB
Chroma1-HDRunsQ6_K7.7 GB10.0 GB
SDXL 1.0Runs well16-bit6.9 GB7.1 GB
Illustrious XL / Pony (SDXL anime)Runs well16-bit6.9 GB7.1 GB
Stable Diffusion 1.5Runs well16-bit2.1 GB3.3 GB
HunyuanImage 2.1Offload onlyQ2_K7.3 GB10.6 GB
video models
Wan 2.1 T2V 14BOffload onlyQ3_K_M7.6 GB11.9 GB
Wan 2.1 T2V 1.3BRuns well16-bit2.8 GB5.6 GB
Wan 2.1 I2V 14B 480POffload onlyQ4_K_M11.3 GB15.6 GB
Wan 2.1 I2V 14B 720POffload onlyQ4_K_M11.3 GB18.1 GB
Wan 2.1 VACE 14BOffload onlyQ4_K_M11.6 GB16.4 GB
Wan 2.2 T2V A14BTightQ2_K5.3 GB9.6 GB
Wan 2.2 I2V A14BTightQ2_K5.3 GB9.6 GB
Wan 2.2 TI2V 5BRuns wellQ8_05.4 GB9.2 GB
Wan 2.2 Animate 14BOffload onlyQ2_K6.5 GB11.8 GB
Wan Animate 2 (14B)Offload onlyQ2_K6.5 GB11.8 GB
Wan 2.2 S2V 14BOffload onlyQ4_K_M13.9 GB18.7 GB
SCAIL-2 (character animation)Offload onlyQ4_K_M11.5 GB16.8 GB
HunyuanVideo (13B, original)Offload onlyQ3_K_M6.2 GB10.5 GB
LTX-Video 13B (0.9.8)TightQ2_K4.7 GB9.0 GB
HunyuanVideo 1.5RunsQ4_K_M5.1 GB9.4 GB
LTX-2 (19B)Offload onlyQ4_K_M12.8 GB17.6 GB
LTX-2.3 (22B)Offload onlyQ4_K_M14.3 GB19.1 GB
LTX-2.5 (22B)Offload onlyQ4_K_M15.1 GB19.9 GB
MiniMax H3 (33B)Offload onlyQ4_K_M19.9 GB25.7 GB
MiniMax H3 PrunedOffload onlyQ4_K_M11.6 GB17.4 GB

Calculated from real file sizes plus working memory. How the numbers work.

02Good to know

The RTX 3080 10 GB (Ampere) has no FP8 compute. FP8 files still load and save memory, but ComfyUI converts them back before the maths, so there is no speed gain — Q8_0 GGUF is the closer-to-original 8-bit choice. ComfyUI can compute INT8 files natively on NVIDIA, which is worth a try where a model offers one.

03Measured and reported results

No measured results yet. Send yours.